Mission 1
# List of packages
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer") # add any you need here
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: viridisLite
##
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose
## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[3]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[4]]
## [1] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[6]]
## [1] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[7]]
## [1] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[8]]
## [1] "rmarkdown" "knitr" "viridis" "viridisLite" "fst"
## [6] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[9]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "questionr" "ggridges" "rmarkdown" "knitr" "viridis"
## [6] "viridisLite" "fst" "RColorBrewer" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[12]]
## [1] "flextable" "questionr" "ggridges" "rmarkdown" "knitr"
## [6] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[13]]
## [1] "infer" "flextable" "questionr" "ggridges" "rmarkdown"
## [6] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [11] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
# read data
ess <- read_fst("All-ESS-Data.fst")
Mission 2
finland_data <- ess %>%
filter(cntry == "FI")
write_fst(finland_data, "~/Desktop/SOC202/Project/finland_data.fst")
Mission 3
rm(list=ls()); gc()
## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 1262926 67.5 2130107 113.8 NA 2130107 113.8
## Vcells 2152136 16.5 1257025468 9590.4 20480 1357338312 10355.7
df <- read_fst("~/Desktop/SOC202/Project/finland_data.fst")
Mission 4
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
finland_data <- df
# make sure you know your current folder path. you can do getwd() to check
finland_data_table_subset <- finland_data %>%
mutate(
health = ifelse(health %in% c(7, 8, 9), NA, health),
happy = ifelse(happy %in% c(77, 88, 99), NA, happy),
aesfdrk = ifelse(aesfdrk %in% c(7, 8, 9), NA, aesfdrk),
)
summary_table <- datasummary_skim(finland_data_table_subset %>% select(health, happy, aesfdrk), output = "flextable")
## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.
summary_table
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
health | 6 | 0 | 2.2 | 0.8 | 1.0 | 2.0 | 5.0 |
happy | 12 | 0 | 8.1 | 1.4 | 0.0 | 8.0 | 10.0 |
aesfdrk | 5 | 0 | 1.7 | 0.7 | 1.0 | 2.0 | 4.0 |
finland_data_v2 <- finland_data_table_subset %>%
rename(
`Subjective General Health` = health,
`How Happy Are You` = happy,
`Feeling Safe Walking Alone in the Dark` = aesfdrk
)
summary_table_v2 <- datasummary_skim(finland_data_v2 %>% select(`Subjective General Health`,`How Happy Are You`, `Feeling Safe Walking Alone in the Dark`), output = "flextable")
## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.
summary_table_v2
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
Subjective General Health | 6 | 0 | 2.2 | 0.8 | 1.0 | 2.0 | 5.0 |
How Happy Are You | 12 | 0 | 8.1 | 1.4 | 0.0 | 8.0 | 10.0 |
Feeling Safe Walking Alone in the Dark | 5 | 0 | 1.7 | 0.7 | 1.0 | 2.0 | 4.0 |
summary_table_v2 <- add_header_lines(summary_table_v2, values = "Table 1: Descriptive Statistics for outcome variables")
summary_table_v2
Table 1: Descriptive Statistics for outcome variables | |||||||
|---|---|---|---|---|---|---|---|
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
Subjective General Health | 6 | 0 | 2.2 | 0.8 | 1.0 | 2.0 | 5.0 |
How Happy Are You | 12 | 0 | 8.1 | 1.4 | 0.0 | 8.0 | 10.0 |
Feeling Safe Walking Alone in the Dark | 5 | 0 | 1.7 | 0.7 | 1.0 | 2.0 | 4.0 |
flextable::save_as_docx(summary_table_v2, path = "summary_table_v2.docx",
width = 10.0, height = 10.0)
Mission 6
avg_happy_by_year <- aggregate(happy ~ year + health, data=finland_data_table_subset, mean)
p1 <- ggplot(avg_happy_by_year, aes(x=year, y=happy, color=as.factor(health))) +
geom_line(aes(group=health)) +
labs(title="Mean of Happiness by year in relation to subjective general health in Finland",
x="Survey Year",
y="Happiness 0 = extremely unhappy - 10 = extremely happy") +
scale_color_discrete(name="Subjective General Health", labels=c("Very good", "Good", "Fair", "Bad", "Very Bad")) +
theme_minimal()
p1
ggsave(filename = "plot1.pdf", plot = p1, device = "pdf", width = 8, height = 6)